LLM-based Visual Code Completion for Aerospace Geometric Design
On the map: Multimodal LLMs / vision-language models → Chart understanding and anomaly detection
Abstract (arXiv)
Recent advances in both Large Language Models (LLMs) and Vision Language Models (VLMs) have seen a step change in their ability to perform visual code completion, but the aerospace industry, which prioritizes safety and explainabilty over rapid LLM adoption, currently has no publicly announced LLM-based geometric design copilot systems in commercial use by aerospace Original Equipment Manufacturers (OEMs). This paper presents a LLM-based visual programming copilot application for aerospace engineering design tasks, using a visual programming variant of the ReAct methodology and GPT 5.4. In addition to the copilot, we describe Wingbuilder, a new Grasshopper plugin library with custom components for aerospace-specific geometry abstraction, and an associated Aerospace Visual Programming Dataset (AVPD) with 18 aerospace expert designed tasks at different levels of difficulty alongside ground truth solutions. We evaluate our copilot application with a user trial involving two experienced aerospace engineers from a large aircraft manufacturing company. We find our copilot visual programming ReAct methodology was successful in generating suggestions that participants found helpful, but slow ReAct inference times limit its usefulness to more complex time-consuming tasks where waiting for good copilot solution suggestion was worthwhile. Participants reported they liked the tool and would be willing to use it in the future.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Chart understanding and anomaly detection, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 13 of its 25 references that are in the map. First posted on arXiv 15 Jun 2026.
Builds on
13 of 25 references.
Closest ancestors · 1
Same direction, newest first
Other references · 12
- 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
- 2021DeepCAD: A Deep Generative Network for Computer-Aided Design Modelscited by 271
- 2025CAD-Llama: Leveraging Large Language Models for Computer-Aided Design Parametric 3D Model Generationcited by 67
- 2024CAD-Assistant: Tool-Augmented VLLMs as Generic CAD Task Solverscited by 40
- 2024Text2CAD: Generating Sequential CAD Models from Beginner-to-Expert Level Text Promptscited by 23
- 2025ComfyUI-R1: Exploring Reasoning Models for Workflow Generationcited by 15
- 2025ComfyUI-Copilot: An Intelligent Assistant for Automated Workflow Developmentcited by 11
- 2024ChatScratch: An AI-Augmented System Toward Autonomous Visual Programming Learning for Children Aged 6-12cited by 7
- 2026SimuAgent: An LLM-Based Simulink Modeling Assistant Enhanced with Reinforcement Learningcited by 5
- 2024ScratchEval: Are GPT-4o Smarter than My Child? Evaluating Large Multimodal Models with Visual Programming Challengescited by 4
- 2024Visual Program Distillation with Template-Based Augmentationcited by 3
- 2025Retrieval-Augmented Fine-Tuning With Preference Optimization For Visual Program Generationcited by 2
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Concise Geometric Description as a Bridge: Unleashing the Potential of LLM for Plane Geometry Problem Solving
- 2026Foundation Models for Automatic CAD Generation
- 2025A Solver-Aided Hierarchical Language for LLM-Driven CAD Design
- 2024Mediating Modes of Thought: LLM's for design scripting
- 2026Training and Benchmarking Code Generation for Physics-Inspired Animations
- 2025LLMs for Engineering: Teaching Models to Design High Powered Rockets
- 2023From Concept to Manufacturing: Evaluating Vision-Language Models for Engineering Design
- 2025CAMB: A comprehensive industrial LLM benchmark on civil aviation maintenance